knitr::opts_knit$set(root.dir = '/Users/charleshanks/desktop/msds/spring_23/ml/FARS2020NationalCSV')
library(tidyverse)
library(tidytext)
library(caret)
library(fastDummies)
library(randomForest)
#intersting in the people driving the vehicle that crashed
drivers = per %>% filter(PER_TYP == 1)
Lot of factors here, this is going to be a lot of dummy cols….
Principal Component Analysis:

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